Skills for Real Engineers. Straight from my .agents directory.
webmcp-gen
Agent skill fromfcakyon/claude-codex-settings
Build and validate experimental WebMCP tools for an existing web page. Use when an agent needs to expose a site's real workflows as page tools, create webmcp.init.js, define deterministic checks, or compare WebMCP with accessibility-tree automation.
How to install webmcp-gen
npx skills add fcakyon/claude-codex-settings# or add only this skill to Claude Code: copy the folder
plugins/agent-browser/skills/webmcp-gen/
# into
~/.claude/skills/webmcp-gen/ (all projects)
.claude/skills/webmcp-gen/ (one project)
1# Generate and validate page WebMCP tools23Create a durable artifact that exposes a real page workflow through WebMCP and proves that the tool behaves like the existing UI.45## Output67Save the work under:89```text10artifacts/<domain>/<task>/11 manifest.json12 webmcp.init.js13 eval.json14 eval-report.md15```1617## Workflow18191. Define the user goal, required initial page state, allowed actions, and consequential actions that need explicit confirmation.202. Explore the page with agent-browser. Record the existing UI behavior, success signal, failure states, and recovery path.213. Write `manifest.json` with the goal, required state, available tools, expected calls, expected UI changes, recovery cases, and excluded secrets.224. Create `webmcp.init.js` and `eval.json`. Prefer declarative WebMCP for semantic HTML forms. Use imperative tools only when the workflow cannot be expressed declaratively.235. Load the script before navigation:2425```bash26agent-browser --init-script ./webmcp.init.js open https://example.com27agent-browser webmcp list28agent-browser webmcp invoke <tool> --params @fixture.json29```30316. Validate registration metadata, input validation, invocation results, visible UI effects, navigation or frame cleanup, invalid state recovery, cancellation, and timeout behavior.327. Save deterministic checks and agent eval cases. Compare at least one task against the accessibility-tree fallback and record success, tool calls, latency, and token use when an external agent is available.33…
Excerpt shown under the repository's Apache-2.0 license.
More skills in claude-codex-settings
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
